VulnerabilityPublished 28 May 2026Updated 18 Jun 2026

CVE-2026-45023: Significant-Gravitas AutoGPT · Unthrottled Resource Allocation

Affects Significant-Gravitas AutoGPTSource CVE Database V5

Compare

Not known to be exploited · CVSS 5.4 Medium : upgrade to 0.6.59 when convenient.

Data as of 30 Oct 2026, 11:52 UTC

CVSS 3.1 base score

5.4Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.2% chance of exploitation in 30 days – higher than 12% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.6.59

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L

Attack Vector: Network
Attack Complexity: Low
Privileges Required: Low
User Interaction: None
Scope: Unchanged
Confidentiality: None
Integrity: Low
Availability: Low

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: None: There is no loss of confidentiality within the impacted component.
Integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 28 May 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 30 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade AutoGPT and significant-gravitas/AutoGPT to 0.6.59.

Affected software

Product	Affected	Fixed in
Significant-GravitasAutoGPT	Affected <0.6.59	Fixed in 0.6.59
GitHubsignificant-gravitas/AutoGPT`pkg:github/significant-gravitas/AutoGPT`Other threats	Affected <0.6.59	Fixed in 0.6.59

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade AutoGPT to version 0.6.59 or later, where this vulnerability is fixed. No other official remediation or temporary fixes are documented. Users should ensure that all API calls are routed through the graph execution path that enforces credit checks. Patch status is confirmed fixed in 0.6.59.

Description

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.

Impact

Users can exploit this vulnerability to execute an unlimited number of blocks without consuming credits, potentially leading to resource exhaustion or denial of service. The integrity of credit-based usage controls is compromised, allowing unauthorized free usage of the platform's resources. There is no direct confidentiality impact reported. The CVSS 3.1 base score is 5.4 (medium severity), reflecting network attack vector, low attack complexity, low privileges required, no user interaction, unchanged scope, no confidentiality impact, limited integrity impact, and limited availability impact.

Summary

CVE-2026-45023 affects Significant-Gravitas AutoGPT, a platform for managing AI agents. The vulnerability arises from a missing credit consumption check in the external API endpoint POST /api/blocks/{block_id}/execute. While the internal graph execution path enforces credit checks, direct calls to this endpoint bypass those checks, allowing users to execute blocks without decrementing their credit balance. This constitutes an allocation of resources without limits or throttling (CWE-770). The vulnerability is resolved in AutoGPT version 0.6.59.

CWE-770Allocation of Resources Without Limits or Throttling (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #25
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
Requirements
Clearly specify the minimum and maximum expectations for capabilities, and dictate which behaviors are acceptable when resource allocation reaches limits.
Architecture and Design
Limit the amount of resources that are accessible to unprivileged users. Set per-user limits for resources. Allow the system administrator to define these limits. Be careful to avoid CWE-410.
Architecture and Design
Design throttling mechanisms into the system architecture. The best protection is to limit the amount of resources that an unauthorized user can cause to be expended.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
OWASP ASVS 4.0.3
V8.1.4 (opens in a new tab)
V13.4.1 (opens in a new tab)
V11.1.4 (opens in a new tab)
Attack patterns
XML Ping of the Death (opens in a new tab)
Exponential Data Expansion (opens in a new tab)
Serialized Data Parameter Blowup (opens in a new tab)
Serialized Data with Nested Payloads (opens in a new tab)
Oversized Serialized Data Payloads (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
CWE-841Improper Enforcement of Behavioral Workflow (opens in a new tab)
Class weaknessOWASP Top 10 A06:2025: Insecure Design (opens in a new tab)
The product supports a session in which more than one behavior must be performed by an actor, but it does not properly ensure that the actor performs the behaviors in the required sequence or timeframe.
OWASP Cheat Sheets
Secure Design Principles (opens in a new tab)
OWASP ASVS 4.0.3
V11.1.1 (opens in a new tab)
V11.1.5 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-8pjg-mfqm-vrhr (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 18 Jun 2026, 17:02 UTC

WeaknessesCWE-770, CWE-841

Technical details

References

Community reviews

Related threats